{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:RBKZ3U6ZGYSQP7R5CMAQNRLJ4D","short_pith_number":"pith:RBKZ3U6Z","canonical_record":{"source":{"id":"2504.01542","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-02T09:30:24Z","cross_cats_sorted":[],"title_canon_sha256":"805bf0be4def17dbd56214d6d1f4280eb9b9333c1de4ca05c9f7d73c985e1213","abstract_canon_sha256":"19883d0ac1ffe5c0dabe7235bc68ad7f6c5841e1edbf0eb6cb07e66439135f8d"},"schema_version":"1.0"},"canonical_sha256":"88559dd3d9362507fe3d130106c569e0d0e5f6b1a3ed500bedab06bfdda54a8f","source":{"kind":"arxiv","id":"2504.01542","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.01542","created_at":"2026-05-25T02:01:03Z"},{"alias_kind":"arxiv_version","alias_value":"2504.01542v2","created_at":"2026-05-25T02:01:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.01542","created_at":"2026-05-25T02:01:03Z"},{"alias_kind":"pith_short_12","alias_value":"RBKZ3U6ZGYSQ","created_at":"2026-05-25T02:01:03Z"},{"alias_kind":"pith_short_16","alias_value":"RBKZ3U6ZGYSQP7R5","created_at":"2026-05-25T02:01:03Z"},{"alias_kind":"pith_short_8","alias_value":"RBKZ3U6Z","created_at":"2026-05-25T02:01:03Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:RBKZ3U6ZGYSQP7R5CMAQNRLJ4D","target":"record","payload":{"canonical_record":{"source":{"id":"2504.01542","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-02T09:30:24Z","cross_cats_sorted":[],"title_canon_sha256":"805bf0be4def17dbd56214d6d1f4280eb9b9333c1de4ca05c9f7d73c985e1213","abstract_canon_sha256":"19883d0ac1ffe5c0dabe7235bc68ad7f6c5841e1edbf0eb6cb07e66439135f8d"},"schema_version":"1.0"},"canonical_sha256":"88559dd3d9362507fe3d130106c569e0d0e5f6b1a3ed500bedab06bfdda54a8f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-25T02:01:03.230498Z","signature_b64":"XxDgw6353iSJYbLLV8a3KgebbujWO6d7qwy+pxjEtbvZz96Rd1ebwZziXRnFJzU9l8q/DvWh0CqdpGwSpk1oDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"88559dd3d9362507fe3d130106c569e0d0e5f6b1a3ed500bedab06bfdda54a8f","last_reissued_at":"2026-05-25T02:01:03.229798Z","signature_status":"signed_v1","first_computed_at":"2026-05-25T02:01:03.229798Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2504.01542","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-25T02:01:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9VTXvk6/1zbkoMSn/xy67zJSq3i6sYqHQ0IBijuHgEx5BXiZvyBRhESvYJZoNyH9p/jcxOkV667cct3xgovkDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T08:50:04.194088Z"},"content_sha256":"3e666694b5ab076ca309630e68d074ee64bd5530cf1ad9ed9b71ebd84e4c618b","schema_version":"1.0","event_id":"sha256:3e666694b5ab076ca309630e68d074ee64bd5530cf1ad9ed9b71ebd84e4c618b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:RBKZ3U6ZGYSQP7R5CMAQNRLJ4D","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Register Always Matters: Analysis of LLM Pretraining Data Through the Lens of Language Variation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Amanda Myntti, Erik Henriksson, Sampo Pyysalo, Veronika Laippala","submitted_at":"2025-04-02T09:30:24Z","abstract_excerpt":"Pretraining data curation is a cornerstone in Large Language Model (LLM) development, leading to growing research on quality filtering of large web corpora. From statistical quality flags to LLM-based labelling systems, datasets are divided into categories, frequently reducing to a binary: those passing the filters are deemed as valuable examples, others are discarded as useless or detrimental. However, a more detailed understanding of the contribution of different kinds of texts to model performance is still largely lacking. In this article, we present the first study utilising registers or g"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.01542","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2504.01542/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-25T02:01:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sYQXMC6o6LFQv6JUTP4QsZU5efDuGDCIRAMDSL1KY6MfDp/Zg9r1JMAve9yr8FKxHFDYljMIvO5Xd9e8nSMxDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T08:50:04.194876Z"},"content_sha256":"e6849579dc78b72a62640d507999a55c15c2049a41c67c097acdf087733f575d","schema_version":"1.0","event_id":"sha256:e6849579dc78b72a62640d507999a55c15c2049a41c67c097acdf087733f575d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RBKZ3U6ZGYSQP7R5CMAQNRLJ4D/bundle.json","state_url":"https://pith.science/pith/RBKZ3U6ZGYSQP7R5CMAQNRLJ4D/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RBKZ3U6ZGYSQP7R5CMAQNRLJ4D/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-05-26T08:50:04Z","links":{"resolver":"https://pith.science/pith/RBKZ3U6ZGYSQP7R5CMAQNRLJ4D","bundle":"https://pith.science/pith/RBKZ3U6ZGYSQP7R5CMAQNRLJ4D/bundle.json","state":"https://pith.science/pith/RBKZ3U6ZGYSQP7R5CMAQNRLJ4D/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RBKZ3U6ZGYSQP7R5CMAQNRLJ4D/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:RBKZ3U6ZGYSQP7R5CMAQNRLJ4D","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"19883d0ac1ffe5c0dabe7235bc68ad7f6c5841e1edbf0eb6cb07e66439135f8d","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-02T09:30:24Z","title_canon_sha256":"805bf0be4def17dbd56214d6d1f4280eb9b9333c1de4ca05c9f7d73c985e1213"},"schema_version":"1.0","source":{"id":"2504.01542","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.01542","created_at":"2026-05-25T02:01:03Z"},{"alias_kind":"arxiv_version","alias_value":"2504.01542v2","created_at":"2026-05-25T02:01:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.01542","created_at":"2026-05-25T02:01:03Z"},{"alias_kind":"pith_short_12","alias_value":"RBKZ3U6ZGYSQ","created_at":"2026-05-25T02:01:03Z"},{"alias_kind":"pith_short_16","alias_value":"RBKZ3U6ZGYSQP7R5","created_at":"2026-05-25T02:01:03Z"},{"alias_kind":"pith_short_8","alias_value":"RBKZ3U6Z","created_at":"2026-05-25T02:01:03Z"}],"graph_snapshots":[{"event_id":"sha256:e6849579dc78b72a62640d507999a55c15c2049a41c67c097acdf087733f575d","target":"graph","created_at":"2026-05-25T02:01:03Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2504.01542/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Pretraining data curation is a cornerstone in Large Language Model (LLM) development, leading to growing research on quality filtering of large web corpora. From statistical quality flags to LLM-based labelling systems, datasets are divided into categories, frequently reducing to a binary: those passing the filters are deemed as valuable examples, others are discarded as useless or detrimental. However, a more detailed understanding of the contribution of different kinds of texts to model performance is still largely lacking. In this article, we present the first study utilising registers or g","authors_text":"Amanda Myntti, Erik Henriksson, Sampo Pyysalo, Veronika Laippala","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-02T09:30:24Z","title":"Register Always Matters: Analysis of LLM Pretraining Data Through the Lens of Language Variation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.01542","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:3e666694b5ab076ca309630e68d074ee64bd5530cf1ad9ed9b71ebd84e4c618b","target":"record","created_at":"2026-05-25T02:01:03Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"19883d0ac1ffe5c0dabe7235bc68ad7f6c5841e1edbf0eb6cb07e66439135f8d","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-02T09:30:24Z","title_canon_sha256":"805bf0be4def17dbd56214d6d1f4280eb9b9333c1de4ca05c9f7d73c985e1213"},"schema_version":"1.0","source":{"id":"2504.01542","kind":"arxiv","version":2}},"canonical_sha256":"88559dd3d9362507fe3d130106c569e0d0e5f6b1a3ed500bedab06bfdda54a8f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"88559dd3d9362507fe3d130106c569e0d0e5f6b1a3ed500bedab06bfdda54a8f","first_computed_at":"2026-05-25T02:01:03.229798Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-25T02:01:03.229798Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"XxDgw6353iSJYbLLV8a3KgebbujWO6d7qwy+pxjEtbvZz96Rd1ebwZziXRnFJzU9l8q/DvWh0CqdpGwSpk1oDQ==","signature_status":"signed_v1","signed_at":"2026-05-25T02:01:03.230498Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.01542","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3e666694b5ab076ca309630e68d074ee64bd5530cf1ad9ed9b71ebd84e4c618b","sha256:e6849579dc78b72a62640d507999a55c15c2049a41c67c097acdf087733f575d"],"state_sha256":"13b99c06edda08c294c6188f3979bb7828cec90eb58eadc5b1caf0684f1e8b5e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Hn3Zh8ORHv9ni68ODcrlRDiOLbX/zVkaCZR9WBjlcuNvstnOU1S+Q0BH6nL1QqXlxdrAdVpYWPisgKIDY8YlDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-26T08:50:04.198850Z","bundle_sha256":"223d76f750c52be37bf434ca0b971069ef323c3c958597a6d7ff440b29585bad"}}